Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3351 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3728. Min Range: -4.3728
Max Act: 4.3728. Min Act: -0.1700
Data Index: 2391285 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3728. Min Range: -4.3728
Max Act: 4.2790. Min Act: -0.1700
Data Index: 4786859 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3728. Min Range: -4.3728
Max Act: 4.2478. Min Act: -0.1700
Data Index: 2482684 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3728. Min Range: -4.3728
Max Act: 4.2165. Min Act: -0.1700
Data Index: 6350357 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3728. Min Range: -4.3728
Max Act: 4.2165. Min Act: -0.1700
Data Index: 3572270 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3728. Min Range: -4.3728
Max Act: 4.1853. Min Act: -0.1700
Data Index: 4796819 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3728. Min Range: -4.3728
Max Act: 4.1540. Min Act: -0.1700
Data Index: 3555971 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3728. Min Range: -4.3728
Max Act: 4.1540. Min Act: -0.1700
Data Index: 2056750 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3728. Min Range: -4.3728
Max Act: 4.1540. Min Act: -0.1700
Data Index: 7927313 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3728. Min Range: -4.3728
Max Act: 4.1540. Min Act: -0.1700
Data Index: 8673278 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3728. Min Range: -4.3728
Max Act: 4.1228. Min Act: -0.1700
Data Index: 4176064 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3728. Min Range: -4.3728
Max Act: 4.1228. Min Act: -0.1700
Data Index: 5914201 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3728. Min Range: -4.3728
Max Act: 4.1228. Min Act: -0.1700
Data Index: 1494131 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3728. Min Range: -4.3728
Max Act: 4.1228. Min Act: -0.1700
Data Index: 4478153 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3728. Min Range: -4.3728
Max Act: 4.1228. Min Act: -0.1700
Data Index: 580172 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3728. Min Range: -4.3728
Max Act: 4.1228. Min Act: -0.1700
Data Index: 7961860 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3728. Min Range: -4.3728
Max Act: 4.1228. Min Act: -0.1700
Data Index: 5245803 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3728. Min Range: -4.3728
Max Act: 4.1228. Min Act: -0.1700
Data Index: 6330986 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3728. Min Range: -4.3728
Max Act: 4.1228. Min Act: -0.1700
Data Index: 670884 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3728. Min Range: -4.3728
Max Act: 4.0915. Min Act: -0.1700
Data Index: 1555226 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19